GraphMemory-IDE: AI-Powered Collaborative Memory Platform

Name: GraphMemory-IDE: AI-Powered Collaborative Memory Platform
Author: elementalcollision

@elementalcollision

GraphMemory-IDE: AI-Powered Collaborative Memory Platform について

AI-assisted development MCP providing long-term, on-device "AI memory" for IDEs. Powered by Kuzu GraphDB and exposed via MCP server

#database #graph #mcp #vscode-extension #cursor #windsurf #mcp-server

基本情報

カテゴリ

開発者ツール

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

elementalcollision

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "GraphMemory-IDE": {
      "command": "docker",
      "args": [
        "compose",
        "up",
        "-d"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is GraphMemory-IDE?

GraphMemory-IDE is an AI-assisted, long-term memory MCP (Model Context Protocol) server for IDEs, powered by the Kuzu graph database. It provides semantic vector search, graph-based knowledge storage, and real-time analytics, integrating with VSCode, Cursor, and Windsurf through dedicated plugins.

How to use GraphMemory-IDE?

Deploy with Docker (recommended): clone the repository, navigate to docker/, and run docker compose up -d. For local development, install dependencies with pip install -r requirements.txt, start the FastAPI server with uvicorn server.main:app --host 0.0.0.0 --port 8080 --reload, and optionally launch the Streamlit dashboard separately. Required environment variables include JWT_SECRET_KEY, DATABASE_URL, REDIS_URL, and KUZU_DB_PATH.

Key features of GraphMemory-IDE

Graph-based memory storage with Kuzu and HNSW vector indexes
Codon-accelerated graph algorithms with 10–100x speedups
FastAPI backend with JWT authentication and rate limiting
Real-time analytics via WebSocket and SSE streaming
Multi-IDE plugin support (VSCode, Cursor, Windsurf)
Production-ready Docker deployment with monitoring stack

Use cases of GraphMemory-IDE

Persistent, retrievable memory for AI-assisted coding sessions
Collaborative knowledge sharing across development teams
Real-time telemetry and analytics for IDE usage patterns
Semantic search over code artifacts and project context

FAQ from GraphMemory-IDE

What is GraphMemory-IDE and how is it different from other memory systems?

GraphMemory-IDE is a dedicated MCP server that combines a Kuzu graph database with semantic vector search, optional Codon-accelerated graph algorithms, and real-time analytics dashboards. It is designed specifically for IDE integration and offers multi-plugin support out of the box.

What are the runtime requirements?

Python 3.11 or higher, with dependencies in requirements.txt. Codon is optional but recommended for high-performance graph algorithms; if not compiled, all operations fall back to NetworkX and numpy. Docker Compose is available for production deployment with PostgreSQL, Redis, Prometheus, and Grafana.

Where is data stored?

Graph data is stored in a Kuzu database at the path specified by KUZU_DB_PATH (default ./data/kuzu). Relational data and sessions are stored in PostgreSQL (default SQLite) and Redis cache respectively.

Does GraphMemory-IDE support authentication?

Yes, the FastAPI server uses JWT authentication with EdDSA/Ed25519 signing. A JWT_SECRET_KEY environment variable must be configured.

What are the known limitations?

Codon acceleration requires manual compilation of native libraries via ./scripts/build_codon.sh and is only beneficial for graphs larger than 100 nodes (configurable). The system is designed for IDE-integrated use; direct API access is available but intended for plugin and dashboard communication.